add tokenizer

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"g": 0, "f": 1, "a": 2, "k": 4, "6": 5, "z": 6, "h": 7, "4": 8, "v": 9, "r": 10, "5": 11, "3": 12, "9": 13, "1": 14, "n": 15, "d": 16, "e": 17, "2": 18, "t": 19, "c": 20, "i": 21, "b": 22, "8": 23, "s": 24, "m": 25, "q": 26, "0": 27, "u": 28, "7": 29, "x": 30, "o": 31, "w": 32, "j": 33, "p": 34, "y": 35, "l": 36, "|": 3, "[UNK]": 37, "[PAD]": 38}